6 papers
Do LLMs Really Need 10+ Thoughts for "Find the Time 1000 Days Later"? Towards Structural Understanding of LLM Overthinking
Xinliang Frederick Zhang, Anhad Mohananey, Alexandra Chronopoulou +5
Models employing long chain-of-thought (CoT) reasoning have shown superior performance on complex reasoning tasks. Yet, this capability introduces a critical and often overlooked i…
Dynamic Classifier-Free Diffusion Guidance via Online Feedback
Pinelopi Papalampidi, Olivia Wiles, Ira Ktena +5
Classifier-free guidance (CFG) is a cornerstone of text-to-image diffusion models, yet its effectiveness is limited by the use of static guidance scales. This "one-size-fits-all" a…
A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames
Pinelopi Papalampidi, Skanda Koppula, Shreya Pathak +7
Understanding long, real-world videos requires modeling of long-range visual dependencies. To this end, we explore video-first architectures, building on the common paradigm of tra…
Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition
Pinelopi Papalampidi, Frank Keller, Mirella Lapata
Movie trailers perform multiple functions: they introduce viewers to the story, convey the mood and artistic style of the film, and encourage audiences to see the movie. These dive…
PaliGemma: A versatile 3B VLM for transfer
Lucas Beyer, Andreas Steiner, André Susano Pinto +32
PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly know…
Memory Consolidation Enables Long-Context Video Understanding
Ivana BalaževiÄ, Yuge Shi, Pinelopi Papalampidi +3
Most transformer-based video encoders are limited to short temporal contexts due to their quadratic complexity. While various attempts have been made to extend this context, this h…